Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    conjunctions, particularly repetitive instances of "and" and "or" used in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dum
    -0.16
    ÙĦس
    -0.15
    icz
    -0.14
    Ø´ÙĪ
    -0.14
    eno
    -0.13
    ãĥªãĤ¹
    -0.13
    ãĤ¢ãĥ¼
    -0.13
    oms
    -0.13
     pÅĻist
    -0.13
    بش
    -0.13
    POSITIVE LOGITS
     alike
    0.16
     Rowe
    0.15
    akov
    0.14
    abelle
    0.14
    ovit
    0.13
     latter
    0.13
     поба
    0.13
    arbonate
    0.13
    ORAGE
    0.13
    ãģĿãģĹãģ¦
    0.13
    Act Density 0.074%

    No Known Activations